Commodity Juxtaposing from Tweets using Sentiment Analysis

Sentiment Analysis is the process of finding the sentiments from different classes of words. Generally speaking, sentiment analysis aims to determine the attitude of a speaker or a writer with respect to some topic or the overall contextual polarity of a document. The attitude may be his or her judgment or evaluation, affective state, or the intended emotional communication. In this case, ‘tweets'! Given a micro-blogging platform where official, verified tweets are available to us, we need to identify the sentiments of those tweets. A model must be constructed where the sentiments are scored, for each product individually and then they are compared with, diagrammatically, portraying users' feedback from the producers stand point. There are many websites that offer a comparison between various products or services based on certain features of the article such as its predominant traits, price, and its welcome in the market and so on. However not many provide a juxtaposing of commodities with user review as the focal point. Those few that do work with Naïve Bayes Machine Learning Algorithms, that poses a disadvantage as it mandatorily assumes that the features, in our project, words, are independent of each other. This is a comparatively inefficient method of performing Sentiment Analysis on bulk text, for official purposes, since sentences will not give the meaning they are supposed to convey, if each word is considered a separate entity. Maximum Entropy Classifier overcomes this draw back by limiting the assumptions it makes of the input data feed, which is what we use in the proposed system.